Re-Visualization Project

Introduction:

OLD VISUALIZATION:

Running Code

When you click the Render button a document will be generated that includes both content and the output of embedded code. You can embed code like this:

# Load required libraries


suppressWarnings({
  library(ggplot2)
  library(plotly)
  library(dplyr)
  library(viridis)  

})
library(ggplot2)
library(readr)
library(maps)

# Load necessary libraries
library(ggplot2)
library(dplyr)
library(plotly)
library(maps)  # For world map data

# Step 1: Load the data
data <- read_csv(
  "C:\\Users\\Venkata\\Desktop\\stat1\\Website project\\website\\suicide-rates-all.csv",
  col_types = cols(
    Country = col_character(),
    Code = col_character(),
    Year = col_double(),
    `suscide-rate` = col_double()
  )
)

# Step 2: Calculate the average suicide rate for each country and round it off to 2 decimal places
avg_suicide_by_country <- data %>%
  group_by(Country) %>%
  summarise(Average_suicide_rate = round(mean(`suscide-rate`, na.rm = TRUE), 2), .groups = "drop")  # Round to 2 decimals

# Step 3: Prepare the world map data
world_map <- map_data("world")

# Step 4: Merge the average suicide data with the world map data
# Make sure the country names match between the datasets (adjust if necessary)
map_data_combined <- world_map %>%
  left_join(avg_suicide_by_country, by = c("region" = "Country"))

# Step 5: Create the map with ggplot
map_plot <- ggplot(map_data_combined, aes(x = long, y = lat, group = group, fill = Average_suicide_rate)) +
  geom_polygon(color = "black") +  # Draw country borders
  scale_fill_gradient(low = "lightcoral", high = "darkred", na.value = "grey50", name = "Avg Suicide Rate per 100,000") +
  labs(title = "Average Suicide Rates by Country (1960-2022)", 
       subtitle = "Based on available data for all years",
       x = "Longitude", 
       y = "Latitude") +
  theme_minimal() +
  theme(
    plot.title = element_text(face = "bold"),
    plot.subtitle = element_text(face = "italic"),
    legend.position = "bottom"
  )

# Step 6: Convert to an interactive plot with plotly
interactive_map <- ggplotly(map_plot, tooltip = c("region", "fill"))

# Show the interactive map
interactive_map

# Read the data
data <- read_csv(
  "C:\\Users\\Venkata\\Desktop\\stat1\\Website project\\website\\suicide-rates-all.csv",
  col_types = cols(
    Country = col_character(),
    Code = col_character(),
    Year = col_double(),
    `suscide-rate` = col_double()
  )
)

# Step 1: Filter data for the year 2010 and calculate the average suicide rate for each country
avg_suicide_by_country_2010 <- data %>%
  filter(Year == 2010) %>%  # Filter for the year 2010
  group_by(Country) %>%
  summarise(Average_suicide_rate = round(mean(`suscide-rate`, na.rm = TRUE), 2), .groups = "drop")  # Round to 2 decimals

# Step 2: Prepare the world map data
world_map <- map_data("world")

# Step 3: Merge the average suicide data for 2010 with the world map data
map_data_combined <- world_map %>%
  left_join(avg_suicide_by_country_2010, by = c("region" = "Country"))

# Step 4: Create the map with ggplot
map_plot <- ggplot(map_data_combined, aes(x = long, y = lat, group = group, fill = Average_suicide_rate)) +
  geom_polygon(color = "black") +  # Draw country borders
  scale_fill_gradient(low = "lightblue", high = "darkblue", na.value = "grey50", name = "Average Suicide Rate per 100,000") +
  labs(title = "Average Suicide Rates by Country in 2010", 
       subtitle = "Based on data for the year 2010",
       x = "Longitude", 
       y = "Latitude") +
  theme_minimal() +
  theme(
    plot.title = element_text(face = "bold"),
    plot.subtitle = element_text(face = "italic"),
    legend.position = "bottom"
  )

# Step 5: Convert to an interactive plot with plotly and set the width and height in ggplotly()
interactive_map <- ggplotly(map_plot, tooltip = c("region", "Average_suicide_rate"))

# Show the interactive map
interactive_map

# Read the data
data <- read_csv(
  "C:\\Users\\Venkata\\Desktop\\stat1\\Website project\\website\\suicide-rates-all.csv",
  col_types = cols(
    Country = col_character(),
    Code = col_character(),
    Year = col_double(),
    `suscide-rate` = col_double()
  )
)

# Step 1: Calculate the average suicide rate for each year
avg_suicide_by_year <- data %>%
  group_by(Year) %>%
  summarise(Average_suicide_rate = mean(`suscide-rate`, na.rm = TRUE), .groups = "drop")

# Step 2: Create the frequency polygon
frequency_polygon <- ggplot(avg_suicide_by_year, aes(x = Year, y = Average_suicide_rate)) +
  geom_line(stat = "identity", color = "blue", size = 1) +  # Line to connect data points
  geom_point(color = "red") +  # Points for each year
  labs(title = "Average Suicide Rates by Year all over the world", 
       x = "Year", 
       y = "Average Suicide Rate per 100,000") +
  theme_minimal() +
  theme(
    plot.title = element_text(face = "bold"), 
    axis.title.x = element_text(face = "bold"), 
    axis.title.y = element_text(face = "bold")
  )

# Convert the frequency polygon to an interactive plot
interactive_frequency_polygon <- ggplotly(frequency_polygon)

# Show the interactive frequency polygon
interactive_frequency_polygon

# Read the data
data <- read_csv(
  "C:\\Users\\Venkata\\Desktop\\stat1\\Website project\\website\\suicide-rates-all.csv",
  col_types = cols(
    Country = col_character(),
    Code = col_character(),
    Year = col_double(),
    `suscide-rate` = col_double()
  )
)

# Step 1: Find top 5 countries with highest average suicide rates
top_5_countries <- data %>%
  group_by(Country) %>%
  summarise(avg_suicide_rate = mean(`suscide-rate`, na.rm = TRUE), .groups = "drop") %>%
  top_n(5, wt = avg_suicide_rate) %>%
  arrange(desc(avg_suicide_rate))

# Step 2: Filter the original data to keep only the top 5 countries
data_top_countries <- data %>%
  filter(Country %in% top_5_countries$Country)

# Step 3: For each of the top 5 countries, find the top 5 years with highest suicide rates
top_5_years <- data_top_countries %>%
  group_by(Country) %>%
  top_n(5, wt = `suscide-rate`) %>%
  arrange(Country, desc(`suscide-rate`))

# Step 4: Create a color palette using viridis
unique_years <- unique(top_5_years$Year)
color_palette <- viridis::viridis(length(unique_years))  # Generate a palette for the unique years

# Step 5: Create the plot using ggplot
plot <- ggplot(top_5_years, aes(x = Country, y = `suscide-rate`, fill = factor(Year))) +
  geom_bar(stat = "identity", position = "dodge") +
  coord_flip() +
  scale_fill_manual(values = color_palette, name = "Year") +  # Use the viridis palette
  labs(title = "Top 5 Years with Highest Suicide Rates in Top 5 Countries", 
       x = "Country", 
       y = "Suicide Rate per 100,000") +
  theme_minimal()

# Step 6: Convert the plot to an interactive plot using plotly
# Create custom tooltip information using the original data
interactive_plot <- ggplotly(plot) %>%
  style(hoverinfo = "text", 
        text = paste("Country: ", top_5_years$Country, "<br>",
                     "Year: ", top_5_years$Year, "<br>",
                     "Suicide Rate: ", top_5_years$`suscide-rate`))

# Show the interactive plot
interactive_plot

# Load necessary libraries
library(ggplot2)
library(dplyr)
library(plotly)
library(rnaturalearth)
library(rnaturalearthdata)
library(sf)

# Load the data
data <- read.csv("C:\\Users\\Venkata\\Desktop\\stat1\\Website project\\website\\suicide-rates-by-age.csv")

# Clean column names for easier access
colnames(data) <- c("Entity", "Code", "Year", 
                    "Death_rate_15_19", "Death_rate_20_24", "Death_rate_25_29", 
                    "Death_rate_30_34", "Death_rate_35_39", "Death_rate_40_44", 
                    "Death_rate_45_49", "Death_rate_50_54", "Death_rate_55_59", 
                    "Death_rate_60_64", "Death_rate_65_69", "Death_rate_70_74", 
                    "Death_rate_75_79", "Death_rate_80_84", "Death_rate_over_85")

# Filter for the 15-19 age group and the most recent year
data_filtered <- data %>%
  filter(!is.na(Death_rate_15_19)) %>%
  group_by(Entity) %>%
  filter(Year == max(Year))  # Choose the most recent year for each country

# Load the world map using the rnaturalearth package
world <- ne_countries(scale = "medium", returnclass = "sf")

# Join suicide data with the world map
world_data <- world %>%
  left_join(data_filtered, by = c("name" = "Entity"))

# Round the death rate to 2 decimal places
world_data$Death_rate_15_19 <- round(world_data$Death_rate_15_19, 2)

# Plot the interactive map using ggplot and plotly
p <- ggplot(world_data) +
  geom_sf(aes(fill = Death_rate_15_19, text = name), color = "white") +
  scale_fill_viridis_c(option = "C", na.value = "grey50") +
  theme_void() +
  labs(fill = "Suicide Rate",
       title = "Suicide Rates for Age 15-19 (Most Recent Year)")

# Convert ggplot to an interactive plotly map, rounding fill values to 2 decimals
interactive_map <- ggplotly(p, tooltip = c("text", "fill")) %>%
  layout(hoverlabel = list(
    namelength = 0,  # Ensure full name is shown
    format = ".2f"   # Display the fill values with 2 decimals in tooltips
  ))

# Show the interactive map
interactive_map

# Load necessary libraries
library(ggplot2)
library(dplyr)
library(plotly)  # For interactive plots

# Load the data
data <- read.csv("C:\\Users\\Venkata\\Desktop\\stat1\\Website project\\website\\suicide-rates-by-age.csv")

# Clean column names for easier access
colnames(data) <- c("Entity", "Code", "Year", 
                    "Death_rate_15_19", "Death_rate_20_24", "Death_rate_25_29", 
                    "Death_rate_30_34", "Death_rate_35_39", "Death_rate_40_44", 
                    "Death_rate_45_49", "Death_rate_50_54", "Death_rate_55_59", 
                    "Death_rate_60_64", "Death_rate_65_69", "Death_rate_70_74", 
                    "Death_rate_75_79", "Death_rate_80_84", "Death_rate_over_85")

# Filter the data for the 15-19 age group and remove missing values
data_filtered <- data %>%
  filter(!is.na(Death_rate_15_19))

# Calculate the average suicide rate for each country across all years, rounded to 2 decimals
avg_suicide_rate <- data_filtered %>%
  group_by(Entity) %>%
  summarise(Avg_Death_rate_15_19 = round(mean(Death_rate_15_19, na.rm = TRUE), 2)) %>%
  arrange(desc(Avg_Death_rate_15_19))

avg_suicide_rate <- avg_suicide_rate %>%
  top_n(20, Avg_Death_rate_15_19)

# Create a color palette
avg_suicide_rate$Color <- scales::rescale(avg_suicide_rate$Avg_Death_rate_15_19)

# Create the interactive plot using plotly
interactive_plot <- ggplot(avg_suicide_rate, aes(x = reorder(Entity, Avg_Death_rate_15_19), 
                                                  y = Avg_Death_rate_15_19, 
                                                  fill = Color)) +
  geom_bar(stat = "identity") +
  coord_flip() +  # Flip coordinates to make country names readable
  scale_fill_gradient(low = "blue", high = "red", na.value = "grey50", 
                      guide = guide_colorbar(title = "Average Rate")) +
  labs(title = "Average Suicide Rate for Age 15-19 (All Years)", 
       x = "Country", 
       y = "Average Suicide Rate per 100,000 Population") +
  theme_minimal() +
  theme(axis.text.y = element_text(angle = 0, hjust = 1)) +  # Keep text horizontal
  theme(plot.margin = margin(10, 10, 10, 40))  # Adjust margins

# Convert ggplot to plotly for interactivity with formatted tooltips
interactive_plotly <- ggplotly(interactive_plot, tooltip = c("x", "y")) %>%
  layout(hoverlabel = list(
    namelength = 0,  # Ensure full name is shown
    format = ".2f"   # Display the y values (Avg_Death_rate_15_19) with 2 decimals in tooltips
  ))

# Show the interactive plot
interactive_plotly